Convert Your Existing FAQ to FAQPage JSON-LD
Paste your existing FAQ (any format — headings, bullet list, table, screenshot) and get back a fully valid Schema.org FAQPage JSON-LD block, plus rewritten visible answers tightened for AI citation. Includes a duplicate-data warning so you don't trigger Rich Results errors.
Pro tip
Adding FAQPage JSON-LD without removing existing FAQ microdata is the #1 cause of Rich Results errors on small business sites. This prompt outputs both the JSON-LD AND a checklist of microdata attributes (itemscope, itemtype, itemprop) you must remove from your visible FAQ before publishing. JSON-LD only — never both.
How to use this prompt
- Pick your AI model. Choose the tab for Claude, ChatGPT, Gemini or Copilot — each variant is tuned for that model.
- Copy the full prompt. Click Copy Full Prompt to copy the text to your clipboard.
- Paste into your AI tool. Open your chosen model and paste the prompt into a new chat.
- Replace the
[placeholders]. Swap any bracketed fields for your company name, audience, product or tone. - Run and refine. Review the output. If anything is off, ask the AI to tighten tone, length or format.
Prompt Variants by Model
Claude
Claude 4.x
FRESH APR 2026
You are a structured-data engineer. I''m going to paste my existing FAQ. Convert it to a paste-ready Schema.org FAQPage JSON-LD block, tighten the answers for AI-engine citation, and warn me about...You are a structured-data engineer. I''m going to paste my existing FAQ. Convert it to a paste-ready Schema.org FAQPage JSON-LD block, tighten the answers for AI-engine citation, and warn me about anything that would break Rich Results validation.
<my_context>
Page URL where this FAQ lives: [https://YOUR-DOMAIN.COM/...]
Business / what you do: [ONE SENTENCE for context]
Brand tone for answer rewrites: [warm-expert / no-nonsense / playful / premium / technical / friendly-everyday]
</my_context>
<existing_faq>
[PASTE YOUR FAQ HERE in any format — headings, bullets, table, copy-paste from a doc. If you have HTML, paste the HTML so I can flag any microdata attributes.]
</existing_faq>
<answer_quality_rules>
For each answer, rewrite it to:
1. Lead with the answer in the first sentence — no preamble, no "Great question".
2. Be 40–90 words.
3. Contain at least one specific fact, number, or example.
4. Be factually defensible.
5. Match the brand tone above.
Do NOT change the question wording unless it''s longer than 12 words or contains brand jargon — flag those for me to approve.
</answer_quality_rules>
Output exactly four sections:
**PART 1 — Audit of Current FAQ**
Markdown table: # · Question (issue if any) · Answer length · Answer issue (if any) · Action (keep / rewrite / split / cut).
**PART 2 — Rewritten Visible FAQ**
The clean Q/A pairs in markdown, ready to replace what''s currently on the page.
**PART 3 — FAQPage JSON-LD (paste-ready)**
A complete <script type="application/ld+json"> block containing the rewritten Q/A pairs as a Schema.org FAQPage. Validate the JSON parses before responding.
**PART 4 — Rich Results Warnings**
- If the original was HTML and contained microdata (itemscope, itemtype="https://schema.org/FAQPage", itemprop="acceptedAnswer", etc.) → list every microdata attribute I must REMOVE from the visible HTML before publishing. Duplicating microdata + JSON-LD is the #1 Rich Results error.
- Any answer where you had to guess at a fact I should verify.
- Any question that should be split into two (compound questions tank citation rates).
End with the exact Rich Results Test URL to validate after I paste: https://search.google.com/test/rich-results?url=[MY-PAGE-URL]
Notes: Claude is strongest at spotting microdata duplication when you paste raw HTML. If your FAQ is in plain text, that warning section will simply be empty — that's fine.
ChatGPT
GPT-5
FRESH APR 2026
Act as a structured-data engineer. I''ll paste my existing FAQ. Convert it to paste-ready FAQPage JSON-LD, tighten the answers for AI citation, and warn me about Rich Results breakers.
My context:
-...Act as a structured-data engineer. I''ll paste my existing FAQ. Convert it to paste-ready FAQPage JSON-LD, tighten the answers for AI citation, and warn me about Rich Results breakers.
My context:
- Page URL where this FAQ lives: [https://YOUR-DOMAIN.COM/...]
- Business / what we do (one sentence): [SENTENCE]
- Brand tone: [warm-expert / no-nonsense / playful / premium / technical / friendly-everyday]
Existing FAQ (paste any format — headings, bullets, table, HTML):
[PASTE]
Answer rewrite rules:
1. First sentence IS the answer. No preamble.
2. 40–90 words.
3. Contains a specific fact, number, or example.
4. Factually defensible.
5. Matches the brand tone.
Do NOT change question wording unless it''s >12 words or contains jargon — flag those for approval.
Output:
1. Audit table: # · Question (issue if any) · Answer length · Answer issue · Action (keep/rewrite/split/cut).
2. Rewritten visible FAQ in markdown.
3. Complete <script type="application/ld+json"> FAQPage block — JSON-valid, paste-ready.
4. Rich Results warnings:
- If I pasted HTML, list every microdata attribute (itemscope, itemtype, itemprop) to REMOVE from the visible markup. JSON-LD + microdata together breaks Rich Results.
- Flag any answer where you guessed at facts.
- Flag compound questions to split.
- End with the Rich Results Test URL: https://search.google.com/test/rich-results?url=[MY-URL]
Notes: GPT-5 is solid here. If it adds an FAQ schema field beyond what Schema.org allows on FAQPage, re-prompt with "stick to FAQPage required + recommended fields only".
Gemini
Gemini 2.5 Pro
FRESH APR 2026
You are a structured-data engineer. I''ll paste my existing FAQ. Convert it to paste-ready Schema.org FAQPage JSON-LD, tighten the answers for AI citation, and flag Rich Results breakers.
MY...You are a structured-data engineer. I''ll paste my existing FAQ. Convert it to paste-ready Schema.org FAQPage JSON-LD, tighten the answers for AI citation, and flag Rich Results breakers.
MY CONTEXT:
• Page URL: [https://YOUR-DOMAIN.COM/...]
• Business / what we do (one sentence): [SENTENCE]
• Brand tone: [warm-expert / no-nonsense / playful / premium / technical / friendly-everyday]
EXISTING FAQ (paste any format — headings, bullets, table, HTML):
[PASTE]
ANSWER REWRITE RULES:
1. First sentence IS the answer.
2. 40–90 words.
3. Contains specific fact / number / example.
4. Factually defensible.
5. Matches brand tone.
Do NOT rewrite question wording unless >12 words or contains jargon — flag those.
OUTPUT:
1. Audit table: # | Question (issue) | Answer length | Answer issue | Action (keep/rewrite/split/cut).
2. Rewritten visible FAQ in markdown.
3. Complete <script type="application/ld+json"> FAQPage block — JSON-valid, paste-ready.
4. Rich Results warnings:
• If HTML pasted, list every microdata attribute (itemscope, itemtype, itemprop) to REMOVE from visible markup.
• Flag answers with guessed facts.
• Flag compound questions to split.
• End with Rich Results Test URL: https://search.google.com/test/rich-results?url=[MY-URL]
Notes: Gemini 2.5 Pro's JSON-LD output is consistently clean. Always validate at https://validator.schema.org as a final check.
Copilot
Copilot (GPT-5)
FRESH APR 2026
Convert my existing FAQ into paste-ready FAQPage JSON-LD, tighten the answers for AI-engine citation, and flag Rich Results breakers.
My context:
• Page URL: [https://YOUR-DOMAIN.COM/...]
• Business...Convert my existing FAQ into paste-ready FAQPage JSON-LD, tighten the answers for AI-engine citation, and flag Rich Results breakers.
My context:
• Page URL: [https://YOUR-DOMAIN.COM/...]
• Business / what we do: [ONE SENTENCE]
• Brand tone: [warm-expert / no-nonsense / playful / premium / technical / friendly-everyday]
Existing FAQ (paste any format — headings, bullets, table, or raw HTML):
[PASTE]
Answer rewrite rules:
1. First sentence IS the answer.
2. 40–90 words.
3. Specific fact / number / example.
4. Factually defensible.
5. Matches brand tone.
Don''t rewrite questions unless >12 words or contains jargon — flag those.
Output:
1. Audit table: # · Question (issue) · Answer length · Answer issue · Action (keep / rewrite / split / cut).
2. Rewritten visible FAQ in markdown.
3. Complete <script type="application/ld+json"> FAQPage block — JSON-valid, paste-ready.
4. Rich Results warnings:
- If HTML pasted, list every microdata attribute (itemscope/itemtype/itemprop) to REMOVE.
- Flag answers where facts were guessed.
- Flag compound questions to split.
- End with the Rich Results Test URL: https://search.google.com/test/rich-results?url=[MY-URL]
Notes: Copilot's output integrates well with Bing's structured-data inspector — useful complement to Google's tester.
Frequently Asked Questions
What does the Convert Your Existing FAQ to FAQPage JSON-LD prompt do?
Paste your existing FAQ (any format — headings, bullet list, table, screenshot) and get back a fully valid Schema.org FAQPage JSON-LD block, plus rewritten visible answers tightened for AI citation. Includes a duplicate-data warning so you don't trigger Rich Results errors.
Which AI models is this prompt tested on?
This prompt is field-tested on Claude, ChatGPT, Gemini and Copilot. Each model has its own optimized variant above.
Do I need a paid AI account to use this prompt?
No. This prompt is written to run on the free tier of Claude, ChatGPT, Gemini and Copilot. Paid tiers simply give you longer context windows and faster responses.
Can I customize this prompt for my business?
Yes. Any text inside square brackets is a placeholder you replace with your own business details, such as company name, audience, product or tone. You can also ask the AI to adjust format, length or style after the first output.
When was this prompt last verified?
Each model variant above shows its own freshness stamp. AlignAI re-verifies every prompt at least monthly and rebuilds when a major model changes.
Don’t see what you need? tailored to your use case.